Renewable Energy Consumption Analysis

Author

Affiliation

Diksha Phuloria, Shruti Elangovan

Rutgers University, New Brunswick

INTRODUCTION

In the face of growing environmental concerns and the depletion of fossil fuel reserves, the transition to renewable energy sources has become a global imperative. Renewable energy derived from natural processes that are continuously replenished such as solar, wind, hydro, and geothermal offers a sustainable and cleaner alternative to traditional energy systems.

This project focuses on analyzing renewable energy consumption trends across various countries from 2000 to 2022. By examining patterns linked to economic development, technological adoption, and energy sector investments, the study aims to uncover key drivers of renewable energy use. The project also forecasts energy consumption for the years 2023 and 2024 and evaluates progress toward global sustainability goals.

DATA SOURCES

To support our analysis, we collected data from four main sources:

Data	Data Type	Source	Time Range
Energy Consumption Data	CSV	Kaggle World Energy Consumption Data. Link	2000 - 2022
GNI Information and Socio-Economic Status for each Country	wbdata Python Module	World Bank’s Data API (wbdata)	2000 - 2022
GDP Information for each Country (Test Data)	Ninjas API	Country wise GDP data API. Link	2023 - 2024
Population Information for each Country (Test Data)	Ninjas API	Country wise population data API. Link	2023 - 2024

DATA PROCESSING

The key data processing steps we took into consideration are:

Data Retrieval - The data was taken form the sources above, the resulting dataframe was a combination of CSV, world bank data, and data pulled via API.

Data Cleaning – We cleaned the dataset, standardizing column names for consistency, and addressing missing values through interpolation or by dropping incomplete rows where appropriate.

Transformation – We standardized time formats, and created new columns like GNI, Socio Economic Status, and per capita energy consumption.

Merging Datasets – Using consistent country codes (ISO) and years, we merged all datasets into a single dataframe aligned by country and time.

Test Data Integration – We added 2023–2024 population, GNI and GDP data, ensuring it matched the structure of our main dataset for accurate prediction modeling.

The first five rows of our processed data is displayed below.

	country	year	iso_code	gdp	population	biofuel_consumption	biofuel_electricity	coal_consumption	coal_electricity	electricity_demand	electricity_generation	electricity_share_energy	fossil_electricity	fossil_fuel_consumption	gas_consumption	gas_electricity	hydro_consumption	hydro_electricity	low_carbon_consumption	low_carbon_electricity	nuclear_consumption	nuclear_electricity	oil_consumption	oil_electricity	other_renewable_consumption	other_renewable_electricity	other_renewable_exc_biofuel_electricity	per_capita_electricity	primary_energy_consumption	renewables_consumption	renewables_electricity	solar_consumption	solar_electricity	wind_consumption	wind_electricity	GNI	Socio-Economic Status
0	Afghanistan	2000	AFG	1.128379e+10	19542986.0	0.0	0.0	0.0	0.0	0.57	0.47	0.0	0.16	0.0	0.0	0.0	0.0	0.31	0.0	0.31	0.0	0.0	0.0	0.16	0.0	0.0	0.0	24.050	5.914	0.0	0.31	0.0	0.0	0.0	0.0	NaN	NaN
1	Afghanistan	2001	AFG	1.102127e+10	19688634.0	0.0	0.0	0.0	0.0	0.69	0.59	0.0	0.09	0.0	0.0	0.0	0.0	0.50	0.0	0.50	0.0	0.0	0.0	0.09	0.0	0.0	0.0	29.967	4.664	0.0	0.50	0.0	0.0	0.0	0.0	NaN	NaN
2	Afghanistan	2002	AFG	1.880487e+10	21000258.0	0.0	0.0	0.0	0.0	0.79	0.69	0.0	0.13	0.0	0.0	0.0	0.0	0.56	0.0	0.56	0.0	0.0	0.0	0.13	0.0	0.0	0.0	32.857	4.428	0.0	0.56	0.0	0.0	0.0	0.0	180.0	Low-income
3	Afghanistan	2003	AFG	2.107434e+10	22645136.0	0.0	0.0	0.0	0.0	1.04	0.94	0.0	0.31	0.0	0.0	0.0	0.0	0.63	0.0	0.63	0.0	0.0	0.0	0.31	0.0	0.0	0.0	41.510	5.208	0.0	0.63	0.0	0.0	0.0	0.0	190.0	Low-income
4	Afghanistan	2004	AFG	2.233257e+10	23553554.0	0.0	0.0	0.0	0.0	0.99	0.89	0.0	0.33	0.0	0.0	0.0	0.0	0.56	0.0	0.56	0.0	0.0	0.0	0.33	0.0	0.0	0.0	37.786	4.810	0.0	0.56	0.0	0.0	0.0	0.0	210.0	Low-income

DATA SUMMARY STATISTICS

The below stated dataframe is the summary statistics for our energy consumption data.

	year	gdp	population	biofuel_consumption	biofuel_electricity	coal_consumption	coal_electricity	electricity_demand	electricity_generation	electricity_share_energy	fossil_electricity	fossil_fuel_consumption	gas_consumption	gas_electricity	hydro_consumption	hydro_electricity	low_carbon_consumption	low_carbon_electricity	nuclear_consumption	nuclear_electricity	oil_consumption	oil_electricity	other_renewable_consumption	other_renewable_electricity	other_renewable_exc_biofuel_electricity	per_capita_electricity	primary_energy_consumption	renewables_consumption	renewables_electricity	solar_consumption	solar_electricity	wind_consumption	wind_electricity	GNI
count	4906.000000	4.906000e+03	4.906000e+03	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.00000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	4906.000000	2183.000000
mean	2010.779861	3.356650e+11	3.292975e+07	3.076598	1.715073	183.751491	38.836549	100.146439	100.369850	5.374279	65.460005	543.30770	146.873270	21.799378	41.230227	16.245405	94.935919	34.783664	33.241138	12.190916	216.639179	4.824078	6.068109	2.077266	0.338628	3513.539697	662.788365	61.711266	22.592748	3.265791	1.230526	8.102476	3.061769	12308.163078
std	6.492154	1.375298e+12	1.307888e+08	23.917948	7.825211	1409.748517	276.279668	471.307293	470.801025	7.521168	329.807788	2512.49669	602.690993	91.052231	200.219805	73.711358	431.681586	152.595062	183.403453	66.445481	866.102241	14.911602	27.223656	8.701784	1.773539	5091.609900	2902.209565	304.850686	107.734160	30.902472	11.686146	64.380731	24.586354	17963.929909
min	2000.000000	0.000000e+00	0.000000e+00	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.00000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	120.000000
25%	2005.000000	0.000000e+00	7.423555e+05	0.000000	0.000000	0.000000	0.000000	0.600000	0.490000	0.000000	0.180000	0.00000	0.000000	0.000000	0.000000	0.000000	0.000000	0.010000	0.000000	0.000000	0.000000	0.040000	0.000000	0.000000	0.000000	295.438000	5.275500	0.000000	0.010000	0.000000	0.000000	0.000000	0.000000	1325.000000
50%	2011.000000	1.926043e+10	5.812102e+06	0.000000	0.000000	0.000000	0.000000	6.860000	6.425000	0.000000	2.170000	0.00000	0.000000	0.000000	0.000000	0.480000	0.000000	0.980000	0.000000	0.000000	0.000000	0.430000	0.000000	0.000000	0.000000	1825.231500	46.337000	0.000000	0.960000	0.000000	0.000000	0.000000	0.000000	4320.000000
75%	2016.000000	1.420203e+11	2.149220e+07	0.000000	0.250000	10.774000	2.490000	41.495000	42.612500	12.845000	23.840000	211.45450	49.649500	9.985000	5.236750	6.310000	20.050250	11.655000	0.000000	0.000000	108.882500	3.220000	0.219250	0.370000	0.000000	4970.334500	300.666000	12.122000	8.830000	0.003000	0.020000	0.015750	0.060000	14880.000000
max	2022.000000	1.815162e+13	1.425894e+09	433.866000	172.130000	24559.486000	5421.190000	8821.430000	8839.130000	33.141000	5710.280000	36318.70700	8812.123000	1689.460000	3471.190000	1321.710000	8137.857000	3128.850000	2303.296000	809.410000	11214.078000	195.620000	563.745000	176.629000	19.160000	56030.785000	44275.914000	7092.607000	2711.220000	1115.113000	420.350000	1988.450000	800.520000	120990.000000

VISUALIZATION

Renewable Energy Consumption Growth

In this section, we analyze the consumption trends of key renewable energy sources — biofuels, solar, wind, and hydro — over time. The visualization clearly illustrates a significant surge in the adoption of most renewable energy sources beginning around 2015. This upward trend highlights a pivotal shift in global energy strategies, as countries increasingly prioritized cleaner and more sustainable alternatives in response to climate change concerns, policy changes, and technological advancements.

Renewable Energy Consumption World Map

A choropleth map was generated to analyze the temporal progress of renewable energy consumption across various countries. While North America initially held the largest share, the map reveals China’s increasing dominance, eventually becoming the global leader in renewable energy consumption.

Non-Renewable Energy Consumption Plots Analysis

Following this, comparable plots were created to examine the trends in non-renewable energy consumption across the years. Though there is a noticable dip in the non-renewable energy resource consumption in 2020, the overall analysis indicates a relatively steady increase in non-renewable energy consumption.

Energy Consumption Comparision Over Time

This analysis examines global energy consumption trends over the years, focusing on the top five consuming nations. While the United States led in 2000, China surpassed it by 2011 and maintained its dominant position through 2022. Notably, renewable energy consumption has increased, especially in China. However, non-renewable sources still remains the dominant energy resource for all countries, highlighting both the advancement of clean energy and the persistent dependence on fossil fuels in major economies.

PREDICTIVE ANALYSIS

Linear Regression Model

• Our goal is to predict renewable energy consumption for the years 2023 and 2024.

• Key predictors used in the model include Year, ISO Code, GDP, and GNI.

• The model achieved an R-squared value of 0.734, indicating a good fit to the data.

Random Forest Model

• The same set of predictors were utilized to model renewable energy consumption using a Random Forest algorithm.

• The model showed an improved performance, with an R² score of 0.801, reflecting a reliable level of predictive accuracy.

As the Random Forest model had the superior performance, achieving a higher R² value of 0.801, we used this model to predict renewable energy consumption for 2023 and 2024. The 5 rows of the predicted data is shown below.

	country	year	population	gdp per capita nominal	gdp per capita ppp	iso_code	GNI	predicted_renewables_consumption
0	Afghanistan	2023	41454761	410.933	2173.745	AFG	380.0	0.14076
1	Albania	2024	2791765	9598.191	21376.586	ALB	NaN	0.00000
2	Albania	2023	2811655	8299.278	20018.303	ALB	7680.0	0.00000
3	Algeria	2024	46814308	5579.128	17718.286	DZA	NaN	7.33403
4	Algeria	2023	46164219	5221.813	16900.136	DZA	4950.0	10.16934

Renewable Energy Consumption (2000–2024)

The time trend plot, generated from our predicted values, illustrates a period of rapid renewable energy consumption growth from 2000 to 2022. However, the flattening of the curve in 2023 and 2024 is likely due to data gaps for a few countries(missing data). Therefore, we cannot definitively confirm the observed dip in energy consumption during these later years.

CONCLUSION

In conclusion, analyzing renewable energy consumption trends across countries over time provides crucial insights into how nations are transitioning effectively toward clean energy sources. This kind of analysis supports governments in setting informed targets and regulations that align with global sustainability goals. Additionally, by leveraging historical trends, we can use predictive modeling to forecast future energy demands, helping them make smarter and more strategic energy planning decisions for the coming years.